Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.8197. Min Act: -0.1700

Data Index: 507147 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.4447. Min Act: -0.1700

Data Index: 628148 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.4759. Min Act: -0.1700

Data Index: 1051468 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.4759. Min Act: -0.1700

Data Index: 1343957 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3822. Min Act: -0.1700

Data Index: 29540 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3822. Min Act: -0.1699

Data Index: 867909 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2884. Min Act: -0.1700

Data Index: 748222 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2884. Min Act: -0.1700

Data Index: 1080936 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2259. Min Act: -0.1700

Data Index: 607269 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3197. Min Act: -0.1700

Data Index: 347862 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1163571 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3197. Min Act: -0.1700

Data Index: 887687 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.3197. Min Act: -0.1699

Data Index: 1259007 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.1634. Min Act: -0.1699

Data Index: 557908 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2259. Min Act: -0.1700

Data Index: 1297386 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.1634. Min Act: -0.1700

Data Index: 1132132 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2884. Min Act: -0.1699

Data Index: 348444 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.1634. Min Act: -0.1699

Data Index: 19228 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.2572. Min Act: -0.1700

Data Index: 675047 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 5.8197. Min Range: -5.8197

Max Act: 5.1322. Min Act: -0.1699

Data Index: 486714 (C4 (Web Text))

Max Activating Token Index: 354